{"total":105,"rows":[{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372,"area":null},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"area":null},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174,"area":null},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"id":"2111.11232","title":"Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms","created":"2021-11-22","cited_by_count":101,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2305.07170","title":"Towards Understanding and Improving GFlowNet Training","created":"2023-05-11","cited_by_count":75,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66,"area":null},{"id":"2101.06521","title":"Hierarchical Reinforcement Learning By Discovering Intrinsic Options","created":"2021-01-16","cited_by_count":58,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"area":null},{"id":"2206.07505","title":"Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2310.07418","title":"Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages","created":"2023-10-11","cited_by_count":28,"area":null},{"id":"2102.04736","title":"Reverb: A Framework For Experience Replay","created":"2021-02-09","cited_by_count":27,"area":null},{"id":"2105.07253","title":"Regret Minimization Experience Replay in Off-Policy Reinforcement Learning","created":"2021-05-15","cited_by_count":25,"area":null},{"id":"2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","created":"2021-02-27","cited_by_count":19,"area":null},{"id":"2203.15845","title":"Topological Experience Replay","created":"2022-03-29","cited_by_count":17,"area":null},{"id":"2207.12141","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","created":"2022-07-25","cited_by_count":17,"area":null},{"id":"2110.01528","title":"Large Batch Experience Replay","created":"2021-10-04","cited_by_count":14,"area":null},{"id":"2310.00386","title":"Order-Preserving GFlowNets","created":"2023-09-30","cited_by_count":13,"area":null},{"id":"2106.03955","title":"Correcting Momentum in Temporal Difference Learning","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2112.09025","title":"Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs","created":"2021-12-16","cited_by_count":12,"area":null},{"id":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2406.18739","title":"RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNets","created":"2024-06-26","cited_by_count":12,"area":null},{"id":"2208.14307","title":"Beyond Supervised Continual Learning: a Review","created":"2022-08-30","cited_by_count":11,"area":null},{"id":"2103.16977","title":"Solving Heterogeneous General Equilibrium Economic Models with Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":10,"area":null},{"id":"2206.12848","title":"Analysis of Stochastic Processes through Replay Buffers","created":"2022-06-26","cited_by_count":9,"area":null},{"id":"2309.15293","title":"Maximum diffusion reinforcement learning","created":"2023-09-26","cited_by_count":9,"area":null},{"id":"2110.02414","title":"Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks","created":"2021-10-05","cited_by_count":8,"area":null},{"id":"2212.04401","title":"A Rubric for Human-like Agents and NeuroAI","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2305.16160","title":"Augmented Memory: Capitalizing on Experience Replay to Accelerate De Novo Molecular Design","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2401.15275","title":"Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks","created":"2024-01-27","cited_by_count":8,"area":null},{"id":"2110.00445","title":"Sim and Real: Better Together","created":"2021-10-01","cited_by_count":7,"area":null},{"id":"2303.17615","title":"Utilizing Reinforcement Learning for de novo Drug Design","created":"2023-03-30","cited_by_count":7,"area":null},{"id":"2306.01276","title":"Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2310.17786","title":"Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2112.04213","title":"Convergence Results For Q-Learning With Experience Replay","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2203.09809","title":"Proximal Policy Optimization with Adaptive Threshold for Symmetric Relative Density Ratio","created":"2022-03-18","cited_by_count":5,"area":null},{"id":"2210.03325","title":"Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2210.11262","title":"RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2308.15039","title":"R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics","created":"2023-08-29","cited_by_count":5,"area":null},{"id":"2409.09702","title":"GFlowNet Pretraining with Inexpensive Rewards","created":"2024-09-15","cited_by_count":5,"area":null},{"id":"2501.08737","title":"Resource-Constrained Federated Continual Learning: What Does Matter?","created":"2025-01-15","cited_by_count":5,"area":null},{"id":"2109.10034","title":"Learning offline: memory replay in biological and artificial reinforcement learning","created":"2021-09-21","cited_by_count":4,"area":null},{"id":"2207.01251","title":"Asynchronous Curriculum Experience Replay: A Deep Reinforcement Learning Approach for UAV Autonomous Motion Control in Unknown Dynamic Environments","created":"2022-07-04","cited_by_count":4,"area":null},{"id":"2302.14188","title":"Exposure-Based Multi-Agent Inspection of a Tumbling Target Using Deep Reinforcement Learning","created":"2023-02-27","cited_by_count":4,"area":null},{"id":"2404.00143","title":"Accelerating Search-Based Planning for Multi-Robot Manipulation by Leveraging Online-Generated Experiences","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2503.06337","title":"Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation","created":"2025-03-08","cited_by_count":4,"area":null},{"id":"2505.23663","title":"AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2102.11319","title":"Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy Reinforcement Learning","created":"2021-02-22","cited_by_count":3,"area":null},{"id":"2210.08065","title":"Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2211.02759","title":"Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI","created":"2022-11-04","cited_by_count":3,"area":null},{"id":"2305.14177","title":"ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2309.16743","title":"High Throughput Training of Deep Surrogates from Large Ensemble Runs","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2105.08990","title":"Improved Exploring Starts by Kernel Density Estimation-Based State-Space Coverage Acceleration in Reinforcement Learning","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2110.08902","title":"On the Convergence of Experience Replay in Policy Optimization: Characterizing Bias, Variance, and Finite-Time Convergence","created":"2021-10-17","cited_by_count":2,"area":null},{"id":"2203.04579","title":"Multi-Objective reward generalization: Improving performance of Deep Reinforcement Learning for applications in single-asset trading","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2205.09869","title":"Transformer with Memory Replay","created":"2022-05-19","cited_by_count":2,"area":null},{"id":"2206.14267","title":"Applications of Reinforcement Learning in Finance -- Trading with a Double Deep Q-Network","created":"2022-06-28","cited_by_count":2,"area":null},{"id":"2207.07791","title":"Associative Memory Based Experience Replay for Deep Reinforcement Learning","created":"2022-07-16","cited_by_count":2,"area":null},{"id":"2303.02234","title":"Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2309.13508","title":"Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout","created":"2023-09-24","cited_by_count":2,"area":null},{"id":"2408.07647","title":"Adaptive Behavioral AI: Reinforcement Learning to Enhance Pharmacy Services","created":"2024-08-14","cited_by_count":2,"area":null},{"id":"2601.01502","title":"Multiscale replay: A robust algorithm for stochastic variational inequalities with a Markovian buffer","created":"2026-01-04","cited_by_count":2,"area":null},{"id":"2601.21624","title":"Training Memory in Deep Neural Networks: Mechanisms, Evidence, and Measurement Gaps","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2102.09139","title":"Algorithmic pricing with independent learners and relative experience replay","created":"2021-02-18","cited_by_count":1,"area":null},{"id":"2208.12341","title":"Variance Reduction based Experience Replay for Policy Optimization","created":"2022-08-25","cited_by_count":1,"area":null},{"id":"2210.00327","title":"Deep Recurrent Q-learning for Energy-constrained Coverage with a Mobile Robot","created":"2022-10-01","cited_by_count":1,"area":null},{"id":"2211.13991","title":"TrustGAN: Training safe and trustworthy deep learning models through generative adversarial networks","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2306.09746","title":"Finite-Time Analysis of Temporal Difference Learning with Experience Replay","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2308.07351","title":"IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2310.11075","title":"Sim-to-Real Transfer of Adaptive Control Parameters for AUV Stabilization under Current Disturbance","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2404.03084","title":"Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2406.14161","title":"Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2409.16098","title":"The Digital Transformation in Health: How AI Can Improve the Performance of Health Systems","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2409.19391","title":"Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training","created":"2024-09-28","cited_by_count":1,"area":null},{"id":"2502.18168","title":"SECURA: Sigmoid-Enhanced CUR Decomposition with Uninterrupted Retention and Low-Rank Adaptation in Large Language Models","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2504.03793","title":"Outlook Towards Deployable Continual Learning for Particle Accelerators","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2111.06907","title":"Improving Experience Replay through Modeling of Similar Transitions' Sets","created":"2021-11-12","cited_by_count":0,"area":null},{"id":"2111.09412","title":"Meta-Reinforcement Learning via Buffering Graph Signatures for Live Video Streaming Events","created":"2021-10-03","cited_by_count":0,"area":null},{"id":"2210.13545","title":"MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2301.11168","title":"Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2302.10311","title":"Understanding the effect of varying amounts of replay per step","created":"2023-02-20","cited_by_count":0,"area":null},{"id":"2304.06055","title":"Sample-Efficient Reinforcement Learning with Symmetry-Guided Demonstrations for Robotic Manipulation","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2306.02766","title":"Networked Communication for Decentralised Agents in Mean-Field Games","created":"2023-06-05","cited_by_count":0,"area":null},{"id":"2307.04841","title":"Loss Dynamics of Temporal Difference Reinforcement Learning","created":"2023-07-10","cited_by_count":0,"area":null},{"id":"2307.09109","title":"Mining of Single-Class by Active Learning for Semantic Segmentation","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2311.00426","title":"Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards","created":"2023-11-01","cited_by_count":0,"area":null},{"id":"2311.02629","title":"Pointer Networks with Q-Learning for Combinatorial Optimization","created":"2023-11-05","cited_by_count":0,"area":null},{"id":"2408.07629","title":"Optimizing HIV Patient Engagement with Reinforcement Learning in Resource-Limited Settings","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2408.08024","title":"Adaptive User Journeys in Pharma E-Commerce with Reinforcement Learning: Insights from SwipeRx","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2412.16079","title":"Fair Distributed Machine Learning with Imbalanced Data as a Stackelberg Evolutionary Game","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2511.03670","title":"DQN Performance with Epsilon Greedy Policies and Prioritized Experience Replay","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2511.04666","title":"Forgetting is Everywhere","created":"2025-11-06","cited_by_count":0,"area":null}],"next_cursor":"100"}